Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    haven

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     starred
    -0.07
     arises
    -0.06
    ogs
    -0.06
     path
    -0.06
     palabras
    -0.06
     Selector
    -0.06
    شت
    -0.06
     Benedict
    -0.06
     Company
    -0.06
     heaven
    -0.06
    POSITIVE LOGITS
     تغ
    0.08
    teri
    0.08
    ินการ
    0.07
    _LSB
    0.06
    coal
    0.06
    ?>
↵
    0.06
    POSE
    0.06
    	lua
    0.06
    _returns
    0.06
     (~(
    0.06
    Act Density 0.012%

    No Known Activations